Jordanian companies’ stock price prediction using hybrid RNN with long term short memory and Tabu list memory

Other Title(s)

تنبؤ أسعار أسهم الشركات الأردنية باستخدام الشبكات العصبية المتكررة الهجينة مع ذاكرة طويلة قصيرة المدى و ذاكرة قائمة Tabu

Dissertant

al-Jumayli, Abd Allah Akram

Thesis advisor

al-Tarawinah, Hassan

University

Middle East University

Faculty

Faculty of Information Technology

Department

Computer Science Department

University Country

Jordan

Degree

Master

Degree Date

2020

English Abstract

Stock price prediction is one of the most challenging tasks for cooperation and how they can make a decision according to this prediction.

The difficulty of stock price prediction raising due to many factors such as market changes and globalization, which pose a challenge for analyzing stock market movements and price behaviors is extremely challenging.

The effective expectation of a stock's future cost could provide business gain and positive impact on the company.

This research propose method Hybrid RNN with Long Term Short Memory and Tabu List and test the proposed method on the benchmark, then apply the method for real Jordanian companies’ historical business records and check predicted stock prices produced by using the proposed method with real stock prices.

Daily stock data has been collected from the Amman Stock Exchange (ASE) in order to train and test the proposed model.

This work aims to provide an accurate method of stock pricing prediction and improve prediction accuracy by removing predicted prices that are far from the real stock price and redundant predictions, to offer a consistent method for the Jordanian companies to survive and flourish in market by analyzing their performance and predict stock price in future to provide them with a tool to avoid bad business decisions and improve their services.

The accuracy of the proposed model is high and promising as the accuracy of RNN with LSTM and Tabu list were better than using only RNN with LSTM as shown in the results, which means that the proposed model can be utilized as a reliable tool for stock prices prediction

Main Topic

Information Technology and Computer Science

No. of Pages

72

Table of Contents

Table of contents.

Abstract.

Abstract in Arabic.

Chapter One : Introduction.

Chapter Two : Background and related works.

Chapter Three : Methodology.

Chapter Four : Experimental results and discussion.

Chapter Five : Conclusion and future work.

References.

American Psychological Association (APA)

al-Jumayli, Abd Allah Akram. (2020). Jordanian companies’ stock price prediction using hybrid RNN with long term short memory and Tabu list memory. (Master's theses Theses and Dissertations Master). Middle East University, Jordan
https://search.emarefa.net/detail/BIM-985368

Modern Language Association (MLA)

al-Jumayli, Abd Allah Akram. Jordanian companies’ stock price prediction using hybrid RNN with long term short memory and Tabu list memory. (Master's theses Theses and Dissertations Master). Middle East University. (2020).
https://search.emarefa.net/detail/BIM-985368

American Medical Association (AMA)

al-Jumayli, Abd Allah Akram. (2020). Jordanian companies’ stock price prediction using hybrid RNN with long term short memory and Tabu list memory. (Master's theses Theses and Dissertations Master). Middle East University, Jordan
https://search.emarefa.net/detail/BIM-985368

Language

English

Data Type

Arab Theses

Record ID

BIM-985368